Neural Network Based Machine Condition Monitoring System

Date
2004-05
Authors
Kaneshige, Kenichi
Contributor
Advisor
Department
Instructor
Depositor
Speaker
Researcher
Consultant
Interviewer
Annotator
Journal Title
Journal ISSN
Volume Title
Publisher
Volume
Number/Issue
Starting Page
Ending Page
Alternative Title
Abstract
In this paper, machine condition monitoring techniques based on multilayered feedfoward neural network (MLFFNN) where the weights in the network are updated based on nodedecoupled extended Kalman filter (NDEKF) training method are proposed. Neural network based techniques have been widely recognized as powerful approaches for condition monitoring system, and the use of NDEKF has better performances in computational complexity and memory requirement among the Kalman filtering algorithm family. The condition monitoring system detects and identifies conditions of components through the neural network based system identification of components. Sensor signals in both time and frequency domains are analyzed to show the effectiveness of the condition monitoring scheme. The performances of diagnostic tools presented in this thesis are evaluated using the cabin temperature control system that is specifically for Boeing 767 as practical application example, and the results show the effectiveness of the developed techniques.
Description
Keywords
Citation
Extent
Format
Geographic Location
Time Period
Related To
Theses for the degree of Master of Science (University of Hawaii at Manoa). Electrical Engineering; no. 3857
Table of Contents
Rights
All UHM dissertations and theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission from the copyright owner.
Rights Holder
Local Contexts
Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.